Can deep learning replace histopathological examinations in the differential diagnosis of cervical lymphadenopathy?

INTRODUCTION: We aimed to develop a diagnostic deep learning model using contrast-enhanced CT images and to investigate whether cervical lymphadenopathies can be diagnosed with these deep learning methods without radiologist interpretations and histopathological examinations. MATERIAL METHOD: A total of 400 patients who underwent surgery for lymphadenopathy in the neck between 2010 and 2022 were retrospectively analyzed. They were examined in four groups of 100 patients: the granulomatous diseases group, the lymphoma group, the squamous cell tumor group, and the reactive hyperplasia group. The diagnoses of the patients were confirmed histopathologically. Two CT images from all the patients in each group were used in the study. The CT images were classified using ResNet50, NASNetMobile, and DenseNet121 architecture input. RESULTS: The classification accuracies obtained with ResNet50, DenseNet121, and NASNetMobile were 92.5%, 90.62, and 87.5, respectively. CONCLUSION: Deep learning is a useful diagnostic tool in diagnosing cervical lymphadenopathy. In the near future, many diseases could be diagnosed with deep learning models without radiologist interpretations and invasive examinations such as histopathological examinations. However, further studies with much larger case series are needed to develop accurate deep-learning models.

Assessment of Bone Conduction Thresholds After Surgical Treatment in Patients with Labyrinthine Fistula.

OBJECTIVE: This study aimed to analyze the bone conduction thresholds before and after surgery in chronic otitis media patients with cholesteatoma who had labyrinthine fistula and whose cholesteatoma matrix had been completely cleaned. METHODS: The study was performed between 2013 to 2017 with 23 chronic otitis media patients who had labyrinthine fistula with cholesteatoma and who were operated at the Department of Otorhinolaryngology of Dicle University School of Medicine. Patients were assessed by anamnesis and examination and when necessary, by temporal computerized tomography and diffusion magnetic resonance imaging. Bone conduction thresholds at frequencies of 500, 1000, 2000, and 4000 Hz were determined by audiometric examination and they were compared before and after surgery. RESULTS: Of the 23 patients, 12 were female and 11 were male; their age range was 10-55 (26.04±14.13) years. In the post-operative period, it was possible to conduct audiological follow-up on 20 patients. In these follow-ups, 16 patients showed no change in bone conduction thresholds, two patients showed worsening, and two showed improvement. When pre- and post-operative bone conduction thresholds at each frequency were compared separately, no significant difference was found (p=0.937). No statistically significant difference was found between the pre- and post-operative means at the four frequencies (p=0.712). CONCLUSION: In this study, we found that to reduce complications relating to cholesteatoma, it might be necessary to completely remove the matrix especially in the case of type 1 and 2 labyrinthine fistulas.

Evaluation of hyperactivity, attention deficit, and impulsivity before and after adenoidectomy/adenotonsillectomy surgery.

OBJECTIVE: The objective of this study was to determine the severity of attention deficit, hyperactivity, and impulsivity symptoms in patients with obstructive airway problems scheduled to undergo adenoidectomy or adenotonsillectomy operation. The effects of the surgical treatment on these symptoms will also be investigated in a case-control design. METHODS: This prospective study included 63 patients (29 girls, 34 boys) who were operated on at the Department of Otorhinolaryngology, Dicle University Medical School, between January 2010 and May 2011 because of obstructive symptoms caused by adenoid or adenotonsillar hypertrophy. The age range of the patients was between 4 and 13 years. The control group consisted of 33 (17 girls, 16 boys) healthy children. RESULTS: Among the patients, 15 children underwent adenoidectomy because of adenoid hypertrophy; 13 patients had adenotonsillectomy because of adenotonsillar hypertrophy, and the remaining patients underwent adenotonsillectomy related with chronic or recurrent tonsillitis with adenoid hypertrophy. Based on the preoperative data, statistically significant difference was observed between the patient and control groups. The patients' attention deficit, hyperactivity, and impulsivity symptoms preoperatively and postoperatively have shown statistically significant differences. CONCLUSIONS: Attention deficit, hyperactivity, and impulsivity symptoms were common among the children who show signs of airway obstruction due to adenotonsillar hypertrophy. Adenoidectomy or adenotonsillectomy operations were both observed to be associated with improvement in these symptoms.

Is preeclampsia a new risk factor for cochlear damage and hearing loss?

OBJECTIVE: We investigated whether preeclampsia is a risk factor for cochlear damage and permanent hearing loss. STUDY DESIGN: Prospective case-control study design. SETTING: Academic tertiary medical center. PATIENTS: Subjects included 40 patients with preeclampsia and 30 healthy pregnant women. INTERVENTIONS: Otoscopic examinations and pure-tone audiometry, tympanometry, otoacoustic emissions (OAEs), and stapedial reflex tests were conducted for all subjects. Negative audiologic tests were reevaluated after the postpartum period. Statistical analyses were performed using χ and binary logistic regression testing. MAIN OUTCOME MEASURES: We searched for signs of middle ear ventilation, damage of cochlea, and sensorineural hearing loss. RESULTS: Eight patients from the preeclampsia group had 1 or more otological problems. Two patients from the control group were determined as having otological problems. Otoacoustic emissions of the right and left ears (p = 0.029, p = 0.044), hearing levels of right and left ear bone conduction (BC) at the 500-Hz frequency (right and left-BC 500), and left ear at the 2,000-Hz frequency (left-BC 2000) differed significantly between the preeclampsia and control groups (p = 0.040, p = 0.003, and p = 0.003). There was no significant difference in the OAEs between the right and left ears in the preeclampsia group (p < 0.05). The variables BC 500-left, BC 500-right, OAE-right, and OAE-left differed significantly between groups based on binary logistic testing. The odds ratio and 95% confidence intervals (95% CI) for these 4 risk variables were as follows: BC 500-left, 1.167 (1.044-1.306); BC 500-right, 1.117 (1.002-1.244); OAE-right, 0.642 (0.505-0.815); and OAE-left, 0.576 (0.475-0.698), respectively. CONCLUSION: Preeclampsia is a risk factor for cochlear damage and permanent hearing loss. Even if preeclampsia resolves after delivery, cochlear damage and permanent hearing loss remain unchanged in patients with preeclampsia.